21 Feb
2012
21 Feb
'12
6:30 p.m.
On 21/02/12 12:24 PM, Sean Conner wrote:
It was thus said that the Great Toby Thain once
stated:
Where do you get 21x from? I see a wall clock ratio of about 12x (still
amazing; can you explain why it's superlinear?)
--Toby
On 21/02/12 12:47 AM, Sean Conner wrote:
I did a test on another sub-section of our codebase at work (this just
happened to have a decently written Makefile). First, a non-parallel make
(same system as above, 8-core SPARC system):
real 4m36.002s
user 4m3.075s
sys 0m29.713s
Now, a parallel make:
real 0m22.330s
user 7m54.787s
sys 0m42.245s
Something like 21 times faster. It was thus said that the Great Alexey Toptygin
once stated:
Impressive. I've yet to see a *super*linear speedup for parallel make,
myself. On Mon, 20 Feb 2012, Peter C. Wallace wrote:
> Much much faster and lower power for multiple low latency coupled tasks
Right. So call me ignorant, and give me some examples of multiple low
latency coupled tasks that can't be easily implemented as a single low
latency task. Why do you need 2+ cores talking to each other? Why not 1
core that is 2+ times as fast?
Not an embedded system, but at work we have access to a multicore SPARC
system (Sun, I don't recall the model since it's actually stashed away in a
data center) with 8 cores. Doing a parallel make (it helps to have a
properly written makefile; I went to the trouble to do so for the part I'm
responsible for) only takes 1/10th the time of a non-parallel make.
-spc (Not bad ... )